Hugging Face's logo

mlfoundations-dev
/
hp_ablations_grid_mistral_bsz2048_lr2e-6_scheduler-cosine-warmup0.15-minlr5e-7

Text Generation
Transformers
Safetensors
mistral
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
d2c92c7
•
1 Parent(s): 9fe9bc8

Training in progress, epoch 3

Browse files
Files changed (4) hide show
  1. model-00001-of-00003.safetensors +1 -1
  2. model-00002-of-00003.safetensors +1 -1
  3. model-00003-of-00003.safetensors +1 -1
  4. trainer_log.jsonl +19 -0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eb121464670505322f39c00b4d938b9a79a9c8fc3951397958e008c806cddf5
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786182eefe2ad980b9053f34f4b47d320209b3d5e204a8f3ecf0aac12fe45741
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33293e3a8986eb4524edff6a42009d8dc1c09f9f6e33451e6253bdf5e92ff316
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59c01c403d65514757b99bb2f025c15ab91d539c1308d6727378c6629879d192
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c89cafdd7aa03b2e26ef31d69ecdfc1397fad448a4ad2e94f2db70c6dedc8b5c
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f195cf93328ff9fda4c7f0e0cdb2a3962e4d22637c6a7385c6cdb0c28f56897f
3
  size 4540516344
trainer_log.jsonl CHANGED
@@ -33,3 +33,22 @@
33
  {"current_steps": 320, "total_steps": 504, "loss": 0.4795, "lr": 1.0861776741666901e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:58:16", "remaining_time": "1:42:30"}
34
  {"current_steps": 330, "total_steps": 504, "loss": 0.4791, "lr": 1.032945093404745e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "3:03:46", "remaining_time": "1:36:53"}
35
  {"current_steps": 336, "total_steps": 504, "eval_loss": 0.061718959361314774, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:08:58", "remaining_time": "1:34:29"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  {"current_steps": 320, "total_steps": 504, "loss": 0.4795, "lr": 1.0861776741666901e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:58:16", "remaining_time": "1:42:30"}
34
  {"current_steps": 330, "total_steps": 504, "loss": 0.4791, "lr": 1.032945093404745e-06, "epoch": 1.9642857142857144, "percentage": 65.48, "elapsed_time": "3:03:46", "remaining_time": "1:36:53"}
35
  {"current_steps": 336, "total_steps": 504, "eval_loss": 0.061718959361314774, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:08:58", "remaining_time": "1:34:29"}
36
+ {"current_steps": 340, "total_steps": 504, "loss": 0.4693, "lr": 9.80881438094648e-07, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "3:12:00", "remaining_time": "1:32:37"}
37
+ {"current_steps": 350, "total_steps": 504, "loss": 0.4599, "lr": 9.302670913558731e-07, "epoch": 2.0833333333333335, "percentage": 69.44, "elapsed_time": "3:17:29", "remaining_time": "1:26:53"}
38
+ {"current_steps": 360, "total_steps": 504, "loss": 0.4552, "lr": 8.813746312151494e-07, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "3:22:58", "remaining_time": "1:21:11"}
39
+ {"current_steps": 370, "total_steps": 504, "loss": 0.4546, "lr": 8.344673626673205e-07, "epoch": 2.2023809523809526, "percentage": 73.41, "elapsed_time": "3:28:28", "remaining_time": "1:15:29"}
40
+ {"current_steps": 380, "total_steps": 504, "loss": 0.4574, "lr": 7.897978996751046e-07, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "3:33:55", "remaining_time": "1:09:48"}
41
+ {"current_steps": 390, "total_steps": 504, "loss": 0.4527, "lr": 7.476068047442332e-07, "epoch": 2.3214285714285716, "percentage": 77.38, "elapsed_time": "3:39:24", "remaining_time": "1:04:08"}
42
+ {"current_steps": 400, "total_steps": 504, "loss": 0.4517, "lr": 7.081212934003984e-07, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "3:44:53", "remaining_time": "0:58:28"}
43
+ {"current_steps": 410, "total_steps": 504, "loss": 0.4507, "lr": 6.715540105448972e-07, "epoch": 2.4404761904761907, "percentage": 81.35, "elapsed_time": "3:50:22", "remaining_time": "0:52:49"}
44
+ {"current_steps": 420, "total_steps": 504, "loss": 0.4505, "lr": 6.381018852787821e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:55:51", "remaining_time": "0:47:10"}
45
+ {"current_steps": 430, "total_steps": 504, "loss": 0.4519, "lr": 6.079450703627314e-07, "epoch": 2.5595238095238093, "percentage": 85.32, "elapsed_time": "4:01:20", "remaining_time": "0:41:31"}
46
+ {"current_steps": 440, "total_steps": 504, "loss": 0.4523, "lr": 5.812459720240681e-07, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "4:06:48", "remaining_time": "0:35:53"}
47
+ {"current_steps": 450, "total_steps": 504, "loss": 0.4498, "lr": 5.581483753357905e-07, "epoch": 2.678571428571429, "percentage": 89.29, "elapsed_time": "4:12:18", "remaining_time": "0:30:16"}
48
+ {"current_steps": 460, "total_steps": 504, "loss": 0.451, "lr": 5.387766698777935e-07, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "4:17:48", "remaining_time": "0:24:39"}
49
+ {"current_steps": 470, "total_steps": 504, "loss": 0.4495, "lr": 5.232351798503945e-07, "epoch": 2.7976190476190474, "percentage": 93.25, "elapsed_time": "4:23:17", "remaining_time": "0:19:02"}
50
+ {"current_steps": 480, "total_steps": 504, "loss": 0.4487, "lr": 5.116076022477671e-07, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "4:28:45", "remaining_time": "0:13:26"}
51
+ {"current_steps": 490, "total_steps": 504, "loss": 0.4454, "lr": 5.039565561169362e-07, "epoch": 2.9166666666666665, "percentage": 97.22, "elapsed_time": "4:34:14", "remaining_time": "0:07:50"}
52
+ {"current_steps": 500, "total_steps": 504, "loss": 0.4473, "lr": 5.003232453297512e-07, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "4:39:44", "remaining_time": "0:02:14"}
53
+ {"current_steps": 504, "total_steps": 504, "eval_loss": 0.06018054857850075, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:44:45", "remaining_time": "0:00:00"}
54
+ {"current_steps": 504, "total_steps": 504, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:45:26", "remaining_time": "0:00:00"}